Market Segmentation
Disclaimer:
All logos, photos, etc. used in this presentation are the property of their respective
copyright owners and are used here for educational purposes only
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.1
STP: Segmentation, Targeting, Positioning
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.2
Segmentation PositioningTargeting
STP
Segmentation:
Subdividing general markets
into distinct segments with
different needs, and which
respond differently to marketing
efforts.
-Increased customer satisfaction
-Increased marketing effectiveness
Targeting:
Selection of market
segments. Cannot
service every possible
segment.
Positioning:
Activities to make consumers
perceive that a brand occupies
a distinct position relative to
competing brands.
STP Advantages
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.3
STP
Advantages
Competitive Advantage
Niche Marketing
Profitability
Concentration of Force
Customer Satisfaction
Focus core competencies
on relevant market segments
Consumers get what they want
Different groups place different
values on similar goods
Hertz: focus on airport rentals
Enterprise: focus on local rentals
Specific segments
with specific needs
Sample Market Segments
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.4
Cost-Oriented Segment
Style-Oriented Segment
Quality-Oriented Segment
Durability-Oriented Segment
Sample
Market
Segments
Rolex Swiss Watches
Briggs and Riley Travelware
GEICO Insurance
Apple Computers
Segment Selection Criteria
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.5
Parsimony
Accessibility
Internal Homogeneity
External Heterogeneity
Segment
Selection
Criteria
Size
Individuals in group respond similarly
One group different from another
As few segments as possible
Easy to reach with marketing
Large enough to be profitable
Response Variable Categories
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.6
Financial
Psychological
Functional
Service and Convenience
Response
Variable
Categories
Usage
Performance; Reliability; Durability
Time savings; Convenience
Usage scenario; Usage rate
Cost savings; Revenue gain
Trust; Esteem; Status
Segmentation Identifier Variables
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.7
Demographics
Geographics
Situational
Consumer
Identifier
Variables
Business
Identifier
Variables
Demographics
Geographics
Psychographics
Age; Income
Country; Region; City
Lifestyle; Interests
Industry; Company size
Company location
Specific applications; Order size
Segmentation Variables
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.8
Independent Variable
Dependent
Variable
Response
Variables
Y Axis
X Axis
Identifier Variables
Relationship between independent
and dependent variables
Market Segmentation: A Priori vs. Post Hoc
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.9
Market
Research
And Analysis
A Priori Post Hoc
Latin: “From Before”
Segments defined before primary
market research and analysis
Latin: “After This”
Segments defined after primary
market research and analysis
A Priori Market Segmentation Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.10
Sample
Design
Data
Collection
Segmentation
Technique
Marketing
Programs
Segmentation
Variables
Step Description
Segmentation Variables Response Variable: Usage rate, etc.
Identifier Variable: Age; Income; etc.
Sample Design Large surveys: Often use random sample
Small surveys: Often use non-random
Data Collection Online survey tools: SurveyMonkey, etc.
Segmentation Technique Cross-tab; Regression; etc.
Marketing Program Leverage information known about segment
Market Segmentation:
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.11
Descriptive
To describe similarities and differences
between groups
Segmentation
Predictive
To predict relationship between independent
and dependent variables
Market Segmentation: Analytic Techniques
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.12
Segmentation Methods
A Priori Post Hoc
Descriptive Predictive Descriptive Predictive
Cross-Tabulation Conjoint Regression
Hierarchical Partitioning
K-MeansWard’s
Clustering
Cross Tabulation: Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.13
Gather
Market
Data
Examine
Market
Data
Construct
Cross-Tab
Table
Interpret
Cross-Tab
Table
Step Description
Gather Market Data Conduct survey to gather response var. info.
as well as identifier variable information
Examine Market Data Consider relationships between response
variable and identifier variables
Construct Cross-Tab Table Use purpose-built tool, or do manually
Interpret Cross-Tab Table Consider how to apply results
Cross Tabulation
Step 1.Gather Market Data
Gather response variable information (Frequency)
as well as identifier variable information: Annual income; Age; Occupation
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.14
Example: Acme Restaurants surveys local community during local town fair.
Goal is to get information for cross-tab segmentation.
Cross Tabulation
Step 2.Examine Market Data
Examine relationship between response variable (frequency) and identifier variables
-Frequency definitely varies by income
-Frequency does not appear to vary by age
-Frequency varies by occupation, but information is redundant with income
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.15
Cross Tabulation
Step 3. Construct Cross-Tab Table
-Use commercial statistics software package such as SPSS and MarketSight
-Or just do it manually
-A Priori Segmentation: Use pre-known bands of independent variable (in this case, Income)
-Count the number of respondents dining out 4 times per month that make $10K-$49K/yr, etc.
-Divide by total to get percentages
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.16
+ many other respondents…
Cross Tabulation
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.17
Step 4. Interpret Cross-Tab Table
-Segment 1: Dining Misers: Low income individuals who dine out rarely
-Segment 2: Dining Medians: Mid-income individuals who dine out occasionally
-Segment 3: Dining Mavens: High-Income individuals who dine out frequently (our target)
Regression-based Segmentation: Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.18
Gather
Market
Data
Examine
Market
Data
Execute
Regression
Analysis
Interpret
Regression
Results
Step Description
Gather Market Data Conduct survey to gather response var. info.
as well as identifier variable information
Examine Market Data Consider relationships between response
variable and identifier variables
Execute Regression Analysis Use Excel Analysis ToolPak
Interpret Regression Results Plug in Part-Worths as regression coefficients
Regression-based Segmentation
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.19
Step 1.Gather Market Data
Gather response variable information (Spending)
as well as identifier variable information: Income
Example: Acme Automobiles wishes to identify segments purchasing used automobiles
Regression-based Segmentation
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.20
Step 2. Examine Market Data
Seek relationships between response variable and identifier variables
A Priori Segmentation: Use pre-known bands of independent variable (in this case, Income)
Alternative: Sort by response variable (dependent variable); Notice gaps in spending
Can use techniques such as K-Means to automate this process
Next step: Find out relationship between income & spending for each segment
3. Regression-based Segmentation: Excel Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.21
3A. Verify Data Linearity
Microsoft Excel: Least Squares Algorithm
Good to plot out data to check if linear
Verify
Data
Linearity
Launch
Data
Analysis
Select
Regression
Analysis
Input
Regression
Data
$6,000
$7,000
$10,000
Spending
Income
$5,000
$8,000
$9,000
$20,000 $25,000 $30,000
3. Regression-based Segmentation: Excel Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.22
3B. Launch Data Analysis
Verify
Data
Linearity
Launch
Data
Analysis
Select
Regression
Analysis
Input
Regression
Data
Excel
Home Data ……
Data Analysis
A B C D E F G
3. Regression-based Segmentation: Excel Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.23
3C. Select “Regression” from Analysis Tools
Verify
Data
Linearity
Launch
Data
Analysis
Select
Regression
Analysis
Input
Regression
Data
Data Analysis
Analysis Tools
OK
Regression
3. Regression-based Segmentation: Excel Process
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.24
3D. Input Regression Data
Y Range: Dependent Variable (Response Variable)
X Range: Independent Variables (could have multiple X variables)
Verify
Data
Linearity
Launch
Data
Analysis
Select
Regression
Analysis
Input
Regression
Data
Regression
Input Y Range OK
Input X Range
Labels
Constant is Zero
Confidence Level: %95x
x
Regression-based Segmentation: Excel Results
R-Squared, the Coefficient of Determination
Also known as “Goodness of Fit”, from 0 (no fit) to 1 (perfect fit)
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.25
Regression-based Segmentation: Excel Results
Spending = 449.339 + (0.290749) * Income
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.26
Results, Segment 1
Spending = (Intercept) + (Income Coefficient) * (Income)
Spending (Buyer 1) = (449.339) + (0.290749) * ($24,000) = $7,427
Spending (Buyer 2) = (7,298.387) + (0.322581) * ($52,000) = $24,073
Spending (Buyer 3) = (25,186.44) + (0.227119) * ($180,000) = $66,068
Segmentation: Cluster Analysis
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.27
Example: Ward’s Example: K-Means
Hierarchical Methods
Cluster Analysis
Partitioning Methods
Ward’s Method:
Agglomerative hierarchical clustering
Groups clusters in hierarchy, from bottom up
Result is a tree-like diagram (dendogram)
K-Means:
Specify K, the number of final clusters to expect
Execute K-Means algorithm
Forms groups based on “distance” from “centroid”
Mathematics and algorithms of Cluster Analysis are complex;
Use cluster analysis built into SAS, SPSS, and other packages
Market Segmentation: Conjoint Analysis
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.28
Bundle
Definitions
Data
Collection
Part-Worths
Calculation
Marketing
Execution
Attribute
Selection
Step Description
Attribute Selection Select characteristics of product/service customers find relevant
Example: Attributes of Screen Size, Processor Speed, Battery Life
Bundle Definitions Define candidate “products” by varying characteristics into “bundles”
Example: Bundles include Laptop A, Laptop B, Laptop C
Data Collection Survey customers on their preferences for different bundles
Part-Worths Calculate desire for each attribute, based on bundle evaluation data
Execution Different segments desire different characteristics
Market Segmentation: Other Techniques
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.29
Targeting: Potential, Alignment, Marketability
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.30
Targeting: Selecting Segments to Support Strategy
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.31
Targeting: Marketing to Target Segments
© Stephan Sorger 2013 www.StephanSorger.com; Marketing Analytics: Market Seg.-Segment. 3.32